# app.py import gradio as gr from bs4 import BeautifulSoup from sentence_transformers import SentenceTransformer import faiss import numpy as np import asyncio import aiohttp import re import base64 import logging import os import sys # Import OpenAI library import openai # Set up logging to output to the console logger = logging.getLogger(__name__) logger.setLevel(logging.INFO) # Create a console handler console_handler = logging.StreamHandler(sys.stdout) console_handler.setLevel(logging.INFO) # Create a formatter and set it for the handler formatter = logging.Formatter('%(asctime)s %(levelname)s %(name)s %(message)s') console_handler.setFormatter(formatter) # Add the handler to the logger logger.addHandler(console_handler) # Initialize models and variables logger.info("Initializing models and variables") embedding_model = SentenceTransformer('all-MiniLM-L6-v2') faiss_index = None bookmarks = [] fetch_cache = {} # Define the categories CATEGORIES = [ "Social Media", "News and Media", "Education and Learning", "Entertainment", "Shopping and E-commerce", "Finance and Banking", "Technology", "Health and Fitness", "Travel and Tourism", "Food and Recipes", "Sports", "Arts and Culture", "Government and Politics", "Business and Economy", "Science and Research", "Personal Blogs and Journals", "Job Search and Careers", "Music and Audio", "Videos and Movies", "Reference and Knowledge Bases", "Dead Link", "Uncategorized", ] # Set up Groq Cloud API key and base URL GROQ_API_KEY = os.getenv('GROQ_API_KEY') if not GROQ_API_KEY: logger.error("GROQ_API_KEY environment variable not set.") # Set OpenAI API key and base URL to use Groq Cloud API openai.api_key = GROQ_API_KEY openai.api_base = "https://api.groq.com/openai/v1" def extract_main_content(soup): """ Extract the main content from a webpage while filtering out boilerplate content. """ if not soup: return "" # Remove script and style elements for element in soup(['script', 'style', 'header', 'footer', 'nav', 'ads', 'sidebar']): element.decompose() # First try to find content in main content areas main_content_tags = soup.find_all(['article', 'main', 'div.content', 'div.post', 'div.entry-content']) if main_content_tags: content = ' '.join([tag.get_text(strip=True, separator=' ') for tag in main_content_tags]) else: # Try to find content in

tags p_tags = soup.find_all('p') if p_tags: content = ' '.join([p.get_text(strip=True, separator=' ') for p in p_tags]) else: # Fallback to body content content = soup.body.get_text(strip=True, separator=' ') if soup.body else soup.get_text(strip=True, separator=' ') # Clean up the text content = ' '.join(content.split()) content = re.sub(r'\s+', ' ', content) # Remove multiple spaces content = re.sub(r'[\n\r\t]', ' ', content) # Remove newlines and tabs # Limit content length to avoid token limits (adjust as needed) return content[:5000] def get_page_metadata(soup): """ Extract metadata from the webpage including title, description, and keywords. """ metadata = { 'title': '', 'description': '', 'keywords': '' } if not soup: return metadata # Get title title_tag = soup.find('title') if title_tag and title_tag.string: metadata['title'] = title_tag.string.strip() # Get meta description (try multiple variants) meta_desc = ( soup.find('meta', attrs={'name': 'description'}) or soup.find('meta', attrs={'property': 'og:description'}) or soup.find('meta', attrs={'name': 'twitter:description'}) ) if meta_desc: metadata['description'] = meta_desc.get('content', '').strip() # Get meta keywords meta_keywords = soup.find('meta', attrs={'name': 'keywords'}) if meta_keywords: metadata['keywords'] = meta_keywords.get('content', '').strip() # Get OG title if main title is empty if not metadata['title']: og_title = soup.find('meta', attrs={'property': 'og:title'}) if og_title: metadata['title'] = og_title.get('content', '').strip() return metadata def generate_summary(bookmark): """ Generate a comprehensive summary for a bookmark using available content and LLM. """ logger.info(f"Generating summary for bookmark: {bookmark.get('url')}") try: # Get the HTML soup object from the bookmark if it exists soup = BeautifulSoup(bookmark.get('html_content', ''), 'html.parser') # Step 1: Extract all available information metadata = get_page_metadata(soup) main_content = extract_main_content(soup) # Step 2: Generate summary using LLM with all available content try: # Prepare comprehensive context for LLM available_content = [] if metadata['title']: available_content.append(f"Title: {metadata['title']}") if metadata['description']: available_content.append(f"Description: {metadata['description']}") if metadata['keywords']: available_content.append(f"Keywords: {metadata['keywords']}") if main_content: available_content.append(f"Main Content: {main_content}") if not available_content: logger.warning("No content available for summary generation") bookmark['summary'] = bookmark.get('title', 'No summary available.') return bookmark prompt = f""" Analyze and summarize this webpage based on the following information: {' | '.join(available_content)} Please provide a concise summary (2-3 sentences) focusing on: 1. The main purpose or topic of the page 2. Key information or features 3. Target audience or use case (if apparent) Be factual and objective. """ response = openai.ChatCompletion.create( model='llama3-8b-8192', messages=[ {"role": "system", "content": "You are a helpful assistant that creates concise webpage summaries."}, {"role": "user", "content": prompt} ], max_tokens=150, temperature=0.5, ) summary = response['choices'][0]['message']['content'].strip() logger.info("Successfully generated LLM summary") bookmark['summary'] = summary return bookmark except Exception as e: logger.error(f"Error generating LLM summary: {e}") # Fallback mechanisms in order of preference if metadata['description']: logger.info("Falling back to meta description") bookmark['summary'] = metadata['description'] elif main_content: logger.info("Falling back to truncated main content") bookmark['summary'] = ' '.join(main_content.split()[:50]) + '...' elif metadata['title']: logger.info("Falling back to title") bookmark['summary'] = metadata['title'] else: bookmark['summary'] = bookmark.get('title', 'No summary available.') return bookmark except Exception as e: logger.error(f"Error in generate_summary: {e}") bookmark['summary'] = bookmark.get('title', 'No summary available.') return bookmark def parse_bookmarks(file_content): """ Parse bookmarks from HTML file. """ logger.info("Parsing bookmarks") try: soup = BeautifulSoup(file_content, 'html.parser') extracted_bookmarks = [] for link in soup.find_all('a'): url = link.get('href') title = link.text.strip() if url and title: extracted_bookmarks.append({'url': url, 'title': title}) logger.info(f"Extracted {len(extracted_bookmarks)} bookmarks") return extracted_bookmarks except Exception as e: logger.error("Error parsing bookmarks: %s", e) raise async def fetch_url_info(session, bookmark): """ Fetch information about a URL asynchronously. """ url = bookmark['url'] if url in fetch_cache: bookmark.update(fetch_cache[url]) return bookmark try: logger.info(f"Fetching URL info for: {url}") headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36' } async with session.get(url, timeout=10, headers=headers) as response: bookmark['etag'] = response.headers.get('ETag', 'N/A') bookmark['status_code'] = response.status if response.status >= 400: bookmark['dead_link'] = True bookmark['description'] = '' bookmark['html_content'] = '' logger.warning(f"Dead link detected: {url} with status {response.status}") else: bookmark['dead_link'] = False content = await response.text() bookmark['html_content'] = content # Store full HTML for summary generation bookmark['description'] = '' # Will be set by generate_summary function logger.info(f"Fetched information for {url}") except Exception as e: bookmark['dead_link'] = True bookmark['etag'] = 'N/A' bookmark['status_code'] = 'N/A' bookmark['description'] = '' bookmark['html_content'] = '' logger.error(f"Error fetching URL info for {url}: {e}") finally: fetch_cache[url] = { 'etag': bookmark.get('etag'), 'status_code': bookmark.get('status_code'), 'dead_link': bookmark.get('dead_link'), 'description': bookmark.get('description'), 'html_content': bookmark.get('html_content', '') } return bookmark async def process_bookmarks_async(bookmarks_list): """ Process all bookmarks asynchronously. """ logger.info("Processing bookmarks asynchronously") try: connector = aiohttp.TCPConnector(limit=5) # Limit concurrent connections timeout = aiohttp.ClientTimeout(total=30) # Set timeout async with aiohttp.ClientSession(connector=connector, timeout=timeout) as session: tasks = [] for bookmark in bookmarks_list: task = asyncio.ensure_future(fetch_url_info(session, bookmark)) tasks.append(task) await asyncio.gather(*tasks) logger.info("Completed processing bookmarks asynchronously") except Exception as e: logger.error(f"Error in asynchronous processing of bookmarks: {e}") raise def assign_category(bookmark): """ Assign a category to a bookmark based on its content. """ if bookmark.get('dead_link'): bookmark['category'] = 'Dead Link' logger.info(f"Assigned category 'Dead Link' to bookmark: {bookmark.get('url')}") return bookmark summary = bookmark.get('summary', '').lower() assigned_category = 'Uncategorized' # Keywords associated with each category category_keywords = { "Social Media": ["social media", "networking", "friends", "connect", "posts", "profile"], "News and Media": ["news", "journalism", "media", "headlines", "breaking news"], "Education and Learning": ["education", "learning", "courses", "tutorial", "university", "academy", "study"], "Entertainment": ["entertainment", "movies", "tv shows", "games", "comics", "fun"], "Shopping and E-commerce": ["shopping", "e-commerce", "buy", "sell", "marketplace", "deals", "store"], "Finance and Banking": ["finance", "banking", "investment", "money", "economy", "stock", "trading"], "Technology": ["technology", "tech", "gadgets", "software", "computers", "innovation"], "Health and Fitness": ["health", "fitness", "medical", "wellness", "exercise", "diet"], "Travel and Tourism": ["travel", "tourism", "destinations", "hotels", "flights", "vacation"], "Food and Recipes": ["food", "recipes", "cooking", "cuisine", "restaurant", "dining"], "Sports": ["sports", "scores", "teams", "athletics", "matches", "leagues"], "Arts and Culture": ["arts", "culture", "museum", "gallery", "exhibition", "artistic"], "Government and Politics": ["government", "politics", "policy", "election", "public service"], "Business and Economy": ["business", "corporate", "industry", "economy", "markets"], "Science and Research": ["science", "research", "experiment", "laboratory", "study", "scientific"], "Personal Blogs and Journals": ["blog", "journal", "personal", "diary", "thoughts", "opinions"], "Job Search and Careers": ["jobs", "careers", "recruitment", "resume", "employment", "hiring"], "Music and Audio": ["music", "audio", "songs", "albums", "artists", "bands"], "Videos and Movies": ["video", "movies", "film", "clips", "trailers", "cinema"], "Reference and Knowledge Bases": ["reference", "encyclopedia", "dictionary", "wiki", "knowledge", "information"], } for category, keywords in category_keywords.items(): for keyword in keywords: if re.search(r'\b' + re.escape(keyword) + r'\b', summary): assigned_category = category logger.info(f"Assigned category '{assigned_category}' to bookmark: {bookmark.get('url')}") break if assigned_category != 'Uncategorized': break bookmark['category'] = assigned_category if assigned_category == 'Uncategorized': logger.info(f"No matching category found for bookmark: {bookmark.get('url')}") return bookmark def vectorize_and_index(bookmarks_list): """ Create vector embeddings for bookmarks and build FAISS index. """ logger.info("Vectorizing summaries and building FAISS index") try: summaries = [bookmark['summary'] for bookmark in bookmarks_list] embeddings = embedding_model.encode(summaries) dimension = embeddings.shape[1] faiss_idx = faiss.IndexFlatL2(dimension) faiss_idx.add(np.array(embeddings)) logger.info("FAISS index built successfully") return faiss_idx, embeddings except Exception as e: logger.error(f"Error in vectorizing and indexing: {e}") raise def display_bookmarks(): """ Generate HTML display for bookmarks. """ logger.info("Generating HTML display for bookmarks") cards = '' for i, bookmark in enumerate(bookmarks): index = i + 1 status = "❌ Dead Link" if bookmark.get('dead_link') else "✅ Active" title = bookmark['title'] url = bookmark['url'] etag = bookmark.get('etag', 'N/A') summary = bookmark.get('summary', '') category = bookmark.get('category', 'Uncategorized') if bookmark.get('dead_link'): card_style = "border: 2px solid var(--error-color);" text_style = "color: var(--error-color);" else: card_style = "border: 2px solid var(--success-color);" text_style = "color: var(--text-color);" card_html = f'''

{index}. {title} {status}

Category: {category}

URL: {url}

ETag: {etag}

Summary: {summary}

''' cards += card_html logger.info("HTML display generated") return cards def process_uploaded_file(file): """ Process the uploaded bookmarks file. """ global bookmarks, faiss_index logger.info("Processing uploaded file") if file is None: logger.warning("No file uploaded") return "Please upload a bookmarks HTML file.", '', gr.update(choices=[]), display_bookmarks() try: file_content = file.decode('utf-8') except UnicodeDecodeError as e: logger.error(f"Error decoding the file: {e}") return "Error decoding the file. Please ensure it's a valid HTML file.", '', gr.update(choices=[]), display_bookmarks() try: bookmarks = parse_bookmarks(file_content) except Exception as e: logger.error(f"Error parsing bookmarks: {e}") return "Error parsing the bookmarks HTML file.", '', gr.update(choices=[]), display_bookmarks() if not bookmarks: logger.warning("No bookmarks found in the uploaded file") return "No bookmarks found in the uploaded file.", '', gr.update(choices=[]), display_bookmarks() # Asynchronously fetch bookmark info try: asyncio.run(process_bookmarks_async(bookmarks)) except Exception as e: logger.error(f"Error processing bookmarks asynchronously: {e}") return "Error processing bookmarks.", '', gr.update(choices=[]), display_bookmarks() # Generate summaries and assign categories for bookmark in bookmarks: generate_summary(bookmark) assign_category(bookmark) try: faiss_index, embeddings = vectorize_and_index(bookmarks) except Exception as e: logger.error(f"Error building FAISS index: {e}") return "Error building search index.", '', gr.update(choices=[]), display_bookmarks() message = f"✅ Successfully processed {len(bookmarks)} bookmarks." logger.info(message) # Generate displays and updates bookmark_html = display_bookmarks() choices = [f"{i+1}. {bookmark['title']} (Category: {bookmark['category']})" for i, bookmark in enumerate(bookmarks)] return message, bookmark_html, gr.update(choices=choices), bookmark_html def delete_selected_bookmarks(selected_indices): """ Delete selected bookmarks. """ global bookmarks, faiss_index if not selected_indices: return "⚠️ No bookmarks selected.", gr.update(choices=[]), display_bookmarks() indices = [int(s.split('.')[0])-1 for s in selected_indices] indices = sorted(indices, reverse=True) for idx in indices: if 0 <= idx < len(bookmarks): logger.info(f"Deleting bookmark at index {idx + 1}") bookmarks.pop(idx) if bookmarks: faiss_index, embeddings = vectorize_and_index(bookmarks) else: faiss_index = None message = "🗑️ Selected bookmarks deleted successfully." logger.info(message) # Update choices and display choices = [f"{i+1}. {bookmark['title']} (Category: {bookmark['category']})" for i, bookmark in enumerate(bookmarks)] return message, gr.update(choices=choices), display_bookmarks() def edit_selected_bookmarks_category(selected_indices, new_category): """ Edit category of selected bookmarks. """ if not selected_indices: return "⚠️ No bookmarks selected.", gr.update(choices=[]), display_bookmarks() if not new_category: return "⚠️ No new category selected.", gr.update(choices=[]), display_bookmarks() indices = [int(s.split('.')[0])-1 for s in selected_indices] for idx in indices: if 0 <= idx < len(bookmarks): bookmarks[idx]['category'] = new_category logger.info(f"Updated category for bookmark {idx + 1} to {new_category}") message = "✏️ Category updated for selected bookmarks." logger.info(message) # Update choices and display choices = [f"{i+1}. {bookmark['title']} (Category: {bookmark['category']})" for i, bookmark in enumerate(bookmarks)] return message, gr.update(choices=choices), display_bookmarks() def export_bookmarks(): """ Export bookmarks to HTML file. """ if not bookmarks: logger.warning("No bookmarks to export") return "⚠️ No bookmarks to export." try: logger.info("Exporting bookmarks to HTML") soup = BeautifulSoup("Bookmarks

Bookmarks

", 'html.parser') dl = soup.new_tag('DL') for bookmark in bookmarks: dt = soup.new_tag('DT') a = soup.new_tag('A', href=bookmark['url']) a.string = bookmark['title'] dt.append(a) dl.append(dt) soup.append(dl) html_content = str(soup) b64 = base64.b64encode(html_content.encode()).decode() href = f'data:text/html;base64,{b64}' logger.info("Bookmarks exported successfully") return f'💾 Download Exported Bookmarks' except Exception as e: logger.error(f"Error exporting bookmarks: {e}") return "⚠️ Error exporting bookmarks." def chatbot_response(user_query): """ Generate chatbot response using Groq Cloud API. """ if not GROQ_API_KEY: logger.warning("GROQ_API_KEY not set.") return "⚠️ API key not set. Please set the GROQ_API_KEY environment variable." if not bookmarks: logger.warning("No bookmarks available for chatbot") return "⚠️ No bookmarks available. Please upload and process your bookmarks first." logger.info(f"Chatbot received query: {user_query}") try: max_bookmarks = 50 bookmark_data = "" for idx, bookmark in enumerate(bookmarks[:max_bookmarks]): bookmark_data += f"{idx+1}. Title: {bookmark['title']}\nURL: {bookmark['url']}\nSummary: {bookmark['summary']}\n\n" prompt = f""" You are an assistant that helps users find relevant bookmarks from their collection based on their queries. User Query: {user_query} Bookmarks: {bookmark_data} Please identify the most relevant bookmarks that match the user's query. Provide a concise list including the index, title, URL, and a brief summary. """ response = openai.ChatCompletion.create( model='llama3-8b-8192', messages=[ {"role": "system", "content": "You help users find relevant bookmarks based on their queries."}, {"role": "user", "content": prompt} ], max_tokens=500, temperature=0.7, ) answer = response['choices'][0]['message']['content'].strip() logger.info("Chatbot response generated using Groq Cloud API") return answer except Exception as e: error_message = f"⚠️ Error processing your query: {str(e)}" logger.error(error_message) return error_message def build_app(): """ Build and launch the Gradio app. """ try: logger.info("Building Gradio app") with gr.Blocks(css="app.css") as demo: # General Overview gr.Markdown(""" # 📚 SmartMarks - AI Browser Bookmarks Manager Welcome to **SmartMarks**, your intelligent assistant for managing browser bookmarks. SmartMarks leverages AI to help you organize, search, and interact with your bookmarks seamlessly. --- ## 🚀 **How to Use SmartMarks** SmartMarks is divided into three main sections: 1. **📂 Upload and Process Bookmarks:** Import your existing bookmarks and let SmartMarks analyze and categorize them for you. 2. **💬 Chat with Bookmarks:** Interact with your bookmarks using natural language queries to find relevant links effortlessly. 3. **🛠️ Manage Bookmarks:** View, edit, delete, and export your bookmarks with ease. """) # Upload and Process Bookmarks Tab with gr.Tab("Upload and Process Bookmarks"): gr.Markdown(""" ## 📂 **Upload and Process Bookmarks** ### 📝 **Steps:** 1. Click on the "Upload Bookmarks HTML File" button 2. Select your bookmarks file 3. Click "Process Bookmarks" to analyze and organize your bookmarks """) upload = gr.File(label="📁 Upload Bookmarks HTML File", type='binary') process_button = gr.Button("⚙️ Process Bookmarks") output_text = gr.Textbox(label="✅ Output", interactive=False) bookmark_display = gr.HTML(label="📄 Processed Bookmarks") # Chat with Bookmarks Tab with gr.Tab("Chat with Bookmarks"): gr.Markdown(""" ## 💬 **Chat with Bookmarks** Ask questions about your bookmarks and get relevant results. """) user_input = gr.Textbox( label="✍️ Ask about your bookmarks", placeholder="e.g., Do I have any bookmarks about AI?" ) chat_button = gr.Button("📨 Send") chat_output = gr.Textbox(label="💬 Response", interactive=False) # Manage Bookmarks Tab with gr.Tab("Manage Bookmarks"): gr.Markdown(""" ## 🛠️ **Manage Bookmarks** Select bookmarks to delete or edit their categories. """) manage_output = gr.Textbox(label="🔄 Status", interactive=False) bookmark_selector = gr.CheckboxGroup( label="✅ Select Bookmarks", choices=[] ) new_category = gr.Dropdown( label="🆕 New Category", choices=CATEGORIES, value="Uncategorized" ) bookmark_display_manage = gr.HTML(label="📄 Bookmarks") with gr.Row(): delete_button = gr.Button("🗑️ Delete Selected") edit_category_button = gr.Button("✏️ Edit Category") export_button = gr.Button("💾 Export") download_link = gr.HTML(label="📥 Download") # Set up event handlers process_button.click( process_uploaded_file, inputs=upload, outputs=[output_text, bookmark_display, bookmark_selector, bookmark_display_manage] ) chat_button.click( chatbot_response, inputs=user_input, outputs=chat_output ) delete_button.click( delete_selected_bookmarks, inputs=bookmark_selector, outputs=[manage_output, bookmark_selector, bookmark_display_manage] ) edit_category_button.click( edit_selected_bookmarks_category, inputs=[bookmark_selector, new_category], outputs=[manage_output, bookmark_selector, bookmark_display_manage] ) export_button.click( export_bookmarks, outputs=download_link ) logger.info("Launching Gradio app") demo.launch(debug=True) except Exception as e: logger.error(f"Error building the app: {e}") print(f"Error building the app: {e}") if __name__ == "__main__": build_app()